GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → npuichigo → ttsflow

npuichigo / ttsflow

Licence: Apache-2.0 license
tensorflow speech synthesis c++ inference for voicenet

Programming Languages

C++
36643 projects - #6 most used programming language
c
50402 projects - #5 most used programming language
Makefile
30231 projects
python
139335 projects - #7 most used programming language

Labels

text-to-speechneural-networktensorflowspeech-synthesis

Projects that are alternatives of or similar to ttsflow

Tensorflowtts
😝 TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
Stars: ✭ 2,382 (+13911.76%)
Mutual labels:  text-to-speech, speech-synthesis
Wavegrad
Implementation of Google Brain's WaveGrad high-fidelity vocoder (paper: https://arxiv.org/pdf/2009.00713.pdf). First implementation on GitHub.
Stars: ✭ 245 (+1341.18%)
Mutual labels:  text-to-speech, speech-synthesis
Wavernn
WaveRNN Vocoder + TTS
Stars: ✭ 1,636 (+9523.53%)
Mutual labels:  text-to-speech, speech-synthesis
Openseq2seq
Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP
Stars: ✭ 1,378 (+8005.88%)
Mutual labels:  text-to-speech, speech-synthesis
Naomi
The Naomi Project is an open source, technology agnostic platform for developing always-on, voice-controlled applications!
Stars: ✭ 171 (+905.88%)
Mutual labels:  text-to-speech, speech-synthesis
Spokestack Python
Spokestack is a library that allows a user to easily incorporate a voice interface into any Python application.
Stars: ✭ 103 (+505.88%)
Mutual labels:  text-to-speech, speech-synthesis
Durian
Implementation of "Duration Informed Attention Network for Multimodal Synthesis" (https://arxiv.org/pdf/1909.01700.pdf) paper.
Stars: ✭ 111 (+552.94%)
Mutual labels:  text-to-speech, speech-synthesis
Tacotron2
A PyTorch implementation of Tacotron2, an end-to-end text-to-speech(TTS) system described in "Natural TTS Synthesis By Conditioning Wavenet On Mel Spectrogram Predictions".
Stars: ✭ 43 (+152.94%)
Mutual labels:  text-to-speech, speech-synthesis
Awesome Ai Services
An overview of the AI-as-a-service landscape
Stars: ✭ 133 (+682.35%)
Mutual labels:  text-to-speech, speech-synthesis
Marytts
MARY TTS -- an open-source, multilingual text-to-speech synthesis system written in pure java
Stars: ✭ 1,699 (+9894.12%)
Mutual labels:  text-to-speech, speech-synthesis
Tacotron 2
DeepMind's Tacotron-2 Tensorflow implementation
Stars: ✭ 1,968 (+11476.47%)
Mutual labels:  text-to-speech, speech-synthesis
Wavegrad
A fast, high-quality neural vocoder.
Stars: ✭ 138 (+711.76%)
Mutual labels:  text-to-speech, speech-synthesis
Merlin
This is now the official location of the Merlin project.
Stars: ✭ 1,168 (+6770.59%)
Mutual labels:  text-to-speech, speech-synthesis
Tacotron Pytorch
A Pytorch Implementation of Tacotron: End-to-end Text-to-speech Deep-Learning Model
Stars: ✭ 104 (+511.76%)
Mutual labels:  text-to-speech, speech-synthesis
Cs224n Gpu That Talks
Attention, I'm Trying to Speak: End-to-end speech synthesis (CS224n '18)
Stars: ✭ 52 (+205.88%)
Mutual labels:  text-to-speech, speech-synthesis
Crystal
Crystal - C++ implementation of a unified framework for multilingual TTS synthesis engine with SSML specification as interface.
Stars: ✭ 108 (+535.29%)
Mutual labels:  text-to-speech, speech-synthesis
Lightspeech
LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search
Stars: ✭ 31 (+82.35%)
Mutual labels:  text-to-speech, speech-synthesis
Wsay
Windows "say"
Stars: ✭ 36 (+111.76%)
Mutual labels:  text-to-speech, speech-synthesis
Pytorch Dc Tts
Text to Speech with PyTorch (English and Mongolian)
Stars: ✭ 122 (+617.65%)
Mutual labels:  text-to-speech, speech-synthesis
Diffwave
DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.
Stars: ✭ 139 (+717.65%)
Mutual labels:  text-to-speech, speech-synthesis
View All Similar Projects ➔

ttsflow

speech synthesis c++ inference for voicenet

ttsflow can be built with both google's bazel build tool and gnu's make. We provide compatibility with bazel for convenience to build from scratch once cloned. However, the final executable file may be really big, which is nearly 60M. The reason is that many unused tensorflow codes are compiled and linked into the final executable file staticly. Maybe it is more suitable to build with gnu's makefile, especially when you want to incorporate tensorflow into your project, so we provide makefile too.

Installation

Method one: build with bazel

It's quite simple to build this project with bazel, just type:

cd ./third_party/tensorflow
./configure
cd ../../
bazel build -c opt --config=opt ttsflow/examples/...

The generated executable file is located in bazel-bin/ttsflow/examples/ttsflow_test

Method two: build with gnu's make

In order to build with tensorflow, you should first compile tensorflow as dynamic-link library.

To build libtensorflow_cc.so for c++, just run:

cd ./third_party/tensorflow
./configure
bazel build -c opt --config=opt //tensorflow:libtensorflow_cc.so

Another prerequisite is protobuf, which should be installed in ttsflow/third_party/protobuf:

cd ./third_party/protobuf
./autogen.sh
./configure --prefix=`pwd`
make
make install

As for vocoder, we use the world vocoder, which is placed in ttsflow/third_party/World:

cd ./third_party/World
make

To compile this project, just directly type make, and a symbolic link named ttsflow_main will be created under the root dir.

make

# Run ttsflow
./ttsflow_main

Also, you can run the test cases after compiling the test files.

make test
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].